Made available in DSpace on 2014-06-11T19:26:55Z (GMT). No. of bitstreams: 0 Previous issue date: 2010-02-26Bitstream added on 2014-06-13T19:47:27Z : No. of bitstreams: 1 almeida_mp_me_sjrp.pdf: 4937582 bytes, checksum: 4d9c67bc8dda1a2e1a742ee59be238fa (MD5) / Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq) / Neste trabalho propõe-se um filtro mediano seletivo e um filtro híbrido para eliminação de ruído impulsivo em imagens digitais monocromáticas. O primeiro é baseado em uma modificação do filtro mediano por meio de um detector de ruído impulsivo. O segundo é obtido combinando-se o filtro mediano seletivo com um modelo de retoque digital. A remoção de ruído impulsivo em uma imagem colorida é realizada por meio da extensão dos filtros propostos para cada canal de cor da imagem. Os experimentos realizados indicam que os métodos propostos são eficazes na restauração de imagens com grandes densidades de ruído. / In this paper a selective median filter and a hybrid filter for removing impulsive noise in digital grayscale images are proposed. The first is a median filter modification based on impulsive noise detector. The second is obtained by combining the selective median filter with a digital inpainting model. The noise removal in color image is obtained by extending the proposed filters for each color channel of the image. The experiments indicated that the proposed methods are powerful in restoring images with high densities noise.

Image segmentation is an essential tool to enhance the ability of computer systems to efficiently perform elementary cognitive tasks such as detection, recognition and tracking. In this thesis we concentrate on the investigation of two fundamental topics in the context of image segmentation: spectral clustering and seeded image segmentation. We introduce two new algorithms for those topics that, in summary, rely on Laplacian-based operators, spectral graph theory, and minimization of energy functionals. The effectiveness of both segmentation algorithms is verified by visually evaluating the resulting partitions against state-of-the-art methods as well as through a variety of quantitative measures typically employed as benchmark by the image segmentation community. Our spectral-based segmentation algorithm combines image decomposition, similarity metrics, and spectral graph theory into a concise and powerful framework. An image decomposition is performed to split the input image into texture and cartoon components. Then, an affinity graph is generated and weights are assigned to the edges of the graph according to a gradient-based inner-product function. From the eigenstructure of the affinity graph, the image is partitioned through the spectral cut of the underlying graph. Moreover, the image partitioning can be improved by changing the graph weights by sketching interactively. Visual and numerical evaluation were conducted against representative spectral-based segmentation techniques using boundary and partition quality measures in the well-known BSDS dataset. Unlike most existing seed-based methods that rely on complex mathematical formulations that typically do not guarantee unique solution for the segmentation problem while still being prone to be trapped in local minima, our segmentation approach is mathematically simple to formulate, easy-to-implement, and it guarantees to produce a unique solution. Moreover, the formulation holds an anisotropic behavior, that is, pixels sharing similar attributes are preserved closer to each other while big discontinuities are naturally imposed on the boundary between image regions, thus ensuring better fitting on object boundaries. We show that the proposed approach significantly outperforms competing techniques both quantitatively as well as qualitatively, using the classical GrabCut dataset from Microsoft as a benchmark. While most of this research concentrates on the particular problem of segmenting an image, we also develop two new techniques to address the problem of image inpainting and photo colorization. Both methods couple the developed segmentation tools with other computer vision approaches in order to operate properly. / Segmentar uma image é visto nos dias de hoje como uma prerrogativa para melhorar a capacidade de sistemas de computador para realizar tarefas complexas de natureza cognitiva tais como detecção de objetos, reconhecimento de padrões e monitoramento de alvos. Esta pesquisa de doutorado visa estudar dois temas de fundamental importância no contexto de segmentação de imagens: clusterização espectral e segmentação interativa de imagens. Foram propostos dois novos algoritmos de segmentação dentro das linhas supracitadas, os quais se baseiam em operadores do Laplaciano, teoria espectral de grafos e na minimização de funcionais de energia. A eficácia de ambos os algoritmos pode ser constatada através de avaliações visuais das segmentações originadas, como também através de medidas quantitativas computadas com base nos resultados obtidos por técnicas do estado-da-arte em segmentação de imagens. Nosso primeiro algoritmo de segmentação, o qual ´e baseado na teoria espectral de grafos, combina técnicas de decomposição de imagens e medidas de similaridade em grafos em uma única e robusta ferramenta computacional. Primeiramente, um método de decomposição de imagens é aplicado para dividir a imagem alvo em duas componentes: textura e cartoon. Em seguida, um grafo de afinidade é gerado e pesos são atribuídos às suas arestas de acordo com uma função escalar proveniente de um operador de produto interno. Com base no grafo de afinidade, a imagem é então subdividida por meio do processo de corte espectral. Além disso, o resultado da segmentação pode ser refinado de forma interativa, mudando-se, desta forma, os pesos do grafo base. Experimentos visuais e numéricos foram conduzidos tomando-se por base métodos representativos do estado-da-arte e a clássica base de dados BSDS a fim de averiguar a eficiência da metodologia proposta. Ao contrário de grande parte dos métodos existentes de segmentação interativa, os quais são modelados por formulações matemáticas complexas que normalmente não garantem solução única para o problema de segmentação, nossa segunda metodologia aqui proposta é matematicamente simples de ser interpretada, fácil de implementar e ainda garante unicidade de solução. Além disso, o método proposto possui um comportamento anisotrópico, ou seja, pixels semelhantes são preservados mais próximos uns dos outros enquanto descontinuidades bruscas são impostas entre regiões da imagem onde as bordas são mais salientes. Como no caso anterior, foram realizadas diversas avaliações qualitativas e quantitativas envolvendo nossa técnica e métodos do estado-da-arte, tomando-se como referência a base de dados GrabCut da Microsoft. Enquanto a maior parte desta pesquisa de doutorado concentra-se no problema específico de segmentar imagens, como conteúdo complementar de pesquisa foram propostas duas novas técnicas para tratar o problema de retoque digital e colorização de imagens.

Cílem této práce je vytvořit neuronovou síť která bude schopna rekonstruovat obličeje z fotografií na kterých je část obličeje překrytá maskou. Jsou prezentovány koncepty využívané při vývoji konvolučních neuronových sítí a generativních kompetitivních sítí. Dále jsou popsány koncepty používané v neuronových sítích specificky pro rekonstrukci fotografií obličejů. Je představen model generativní kompetitivní sítě využívající kombinaci hrazených konvolučních vrstev a víceškálových bloků schopný realisticky doplnit oblasti obličeje zakryté maskou.

Cette thèse concerne le problème de désocclusion d'images, au moyen des équations aux dérivées partielles. Dans la première partie de la thèse, la désocclusion est modélisée par un problème de Cauchy qui consiste à déterminer une solution d'une équation aux dérivées partielles avec des données aux bords accessibles seulement sur une partie du bord de la partie à recouvrir. Ensuite, on a utilisé des algorithmes de minimisation issus de la théorie des jeux, pour résoudre ce problème de Cauchy. La deuxième partie de la thèse est consacrée au choix des paramètres de régularisation pour des EDP d'ordre deux et d'ordre quatre. L'approche développée consiste à construire une famille de problèmes d'optimisation bien posés où les paramètres sont choisis comme étant une fonction variable en espace. Ceci permet de prendre en compte les différents détails, à différents échelles dans l'image. L'apport de la méthode est de résoudre de façon satisfaisante et objective, le choix du paramètre de régularisation en se basant sur des indicateurs d'erreur et donc le caractère à posteriori de la méthode (i.e. indépendant de la solution exacte, en générale inconnue). En outre, elle fait appel à des techniques classiques d'adaptation de maillage, qui rendent peu coûteuses les calculs numériques. En plus, un des aspects attractif de cette méthode, en traitement d'images est la récupération et la détection de contours et de structures fines. / Image inpainting refers to the process of restoring a damaged image with missing information. Different mathematical approaches were suggested to deal with this problem. In particular, partial differential diffusion equations are extensively used. The underlying idea of PDE-based approaches is to fill-in damaged regions with available information from their surroundings. The first purpose of this Thesis is to treat the case where this information is not available in a part of the boundary of the damaged region. We formulate the inpainting problem as a nonlinear boundary inverse problem for incomplete images. Then, we give a Nash-game formulation of this Cauchy problem and we present different numerical which show the efficiency of the proposed approach as an inpainting method.Typically, inpainting is an ill-posed inverse problem for it most of PDEs approaches are obtained from minimization of regularized energies, in the context of Tikhonov regularization. The second part of the thesis is devoted to the choice of regularization parameters in second-and fourth-order energy-based models with the aim of obtaining as far as possible fine features of the initial image, e.g., (corners, edges, … ) in the inpainted region. We introduce a family of regularized functionals with regularization parameters to be selected locally, adaptively and in a posteriori way allowing to change locally the initial model. We also draw connections between the proposed method and the Mumford-Shah functional. An important feature of the proposed method is that the investigated PDEs are easy to discretize and the overall adaptive approach is easy to implement numerically.

The visualization of a 3D image obtained from computerized tomography examinations has shown itself to be an important factor for increasing the quality of medical diagnoses and, consequently, treatment efficacy. There already exist on the market, several visualization softwares, which use different techniques to show the 3D tomography image. However, to show a high quality 3D image, sophisticated devices must be used to obtain slices, close to one another, thus increasing the incidence of X-ray given to the patient. An interpolation slice method which resulted from the TC examination produces good results, and is able to reduce the X-ray incidence upon the patient. This method must reconstruct the curvature from the patient s internal structures without using slices in close proximity. This work proposes a method of 3D image interpolation, composed of a juxtaposition of the slices from CT examination results. The goal of this method is to increase the quality of 3D visualization through the production of sharp and precise structure contours. This thesis proposes the division of the interpolation method into two steps. In the first step, the goal is to obtain an initial representation of the image in 3D, which is composed of real slices as well as virtual slices which are referred to in this work as initial virtual slices. In the second step, the empty spaces of the structure are recovered by the 3D image inpainting process. This work also proposes a method to obtain the initial virtual slice and two different methods for inpainting the 3D image. These inpainting methods are the transversal slice line prolongation method and the transportation and diffusion of information. Both methods use the differential equation theory. The transportation and diffusion of information method shows better results than other methods proposed in this work, besides this, this method presents better results than the linear interpolation and Goshtasby et al. [1] methods also implemented in this work. Visual and numerical comparisons are used to obtain this conclusion. The numerical measures used are statistical correlation, the PSNR and the Hausdorff distance [2]. The transportation and diffusion of information method shows itself able to produce better results than all the other tested methods. Besides this principal contribution, this work also developed a KIT to implement 2D and 3D CT visualize applications. / A visualização de imagens resultantes de exame de tomografia computadorizada (TC) em 3D ´e um fator importante para o aumento da precisão nos diagnósticos médicos e, consequentemente, na eficácia dos tratamentos. Atualmente existem diversos produtos no mercado, que fazem uso de várias técnicas existentes para apresentação de imagens tomográficas em 3D. Contudo, para se obter maior suavidade e precisão nos contornos das estruturas visualizadas em 3D, utiliza-se equipamentos capazes de produzir fatias paralelas do corpo humano muito próximas uma das outras, aumentando a exposição dos pacientes aos raios X. Um método de interpolação de fatias resultantes de exame de TC que forneça bons resultados, pode reduzir a incidência de raios X no paciente, pois esse método pode recuperar a curvatura das estruturas sem a necessidade de uma grande proximidade entre as fatias. Este trabalho propõe um método para a interpolação de imagem em 3D, formada pela justaposição de fatias de resultados de exames de tomografia computadorizada. O objetivo desse método ´e obter contornos suaves e precisos, melhorando os processos de visualização em 3D. Para isso, esta tese propõe a divisão do processo de interpolação em duas etapas. Na primeira etapa obtém-se uma representação inicial da imagem em 3D composta por fatias reais e por fatias denominadas de fatias virtuais iniciais e, na segunda etapa, restaura-se essas estruturas geradas com um processo de retoque de imagem em 3D. Este trabalho propõe também um método para obtenção da fatia virtual inicial e dois métodos diferentes para a realização do passo de retoque da imagem em 3D resultante da justaposição das fatias reais e virtuais iniciais. Esses métodos são o prolongamento de linhas nas fatias transversais e transporte e difusão de informações. Ambos os métodos utilizam a teoria de equações diferenciais. O método de transporte e difusão de informações demonstrou melhores resultados do que outro método proposto neste trabalho, além de obter melhores resultados do que os métodos de interpolação linear e Goshtasby e outros [1] implementados neste trabalho. Comparações visuais e comparações numéricas utilizando a correlação estatística, a PSNR e a distância de Haussdorff [2] foram realizadas para se obter essas conclusões. O método de transporte e difusão de informações é capaz de gerar contornos mais suaves e precisos que esses outros métodos testados. Além dessa contribuição principal, este trabalho também desenvolveu um KIT para a construção de aplicações visualizadoras de tomografias computadorizadas em 2D e em 3D. / Mestre em Ciências

Variational methods and Partial Differential Equations (PDEs) have been extensively employed for the mathematical formulation of a myriad of problems describing physical phenomena such as heat propagation, thermodynamic transformations and many more. In imaging, PDEs following variational principles are often considered. In their general form these models combine a regularisation and a data fitting term, balancing one against the other appropriately. Total variation (TV) regularisation is often used due to its edgepreserving and smoothing properties. In this thesis, we focus on the design of TV-based models for several different applications. We start considering PDE models encoding higher-order derivatives to overcome wellknown TV reconstruction drawbacks. Due to their high differential order and nonlinear nature, the computation of the numerical solution of these equations is often challenging. In this thesis, we propose directional splitting techniques and use Newton-type methods that despite these numerical hurdles render reliable and efficient computational schemes. Next, we discuss the problem of choosing the appropriate data fitting term in the case when multiple noise statistics in the data are present due, for instance, to different acquisition and transmission problems. We propose a novel variational model which encodes appropriately and consistently the different noise distributions in this case. Balancing the effect of the regularisation against the data fitting is also crucial. For this sake, we consider a learning approach which estimates the optimal ratio between the two by using training sets of examples via bilevel optimisation. Numerically, we use a combination of SemiSmooth (SSN) and quasi-Newton methods to solve the problem efficiently. Finally, we consider TV-based models in the framework of graphs for image segmentation problems. Here, spectral properties combined with matrix completion techniques are needed to overcome the computational limitations due to the large amount of image data. Further, a semi-supervised technique for the measurement of the segmented region by means of the Hough transform is proposed.

Cette thèse se situe dans le cadre de l'analyse théorique et numérique de quelques généralisations de l'équation de Cahn-Hilliard. On étudie l'existence, l'unicité et la régularité de la solution de ces modèles ainsi que son comportement asymptotique en terme d'existence d'un attracteur global de dimension fractale finie. La première partie de la thèse concerne des modèles appliqués à la retouche d'images. D'abord, on étudie la dynamique de l'équation de Bertozzi-Esedoglu-Gillette-Cahn-Hilliard avec des conditions de type Neumann sur le bord et une nonlinéarité régulière de type polynomial et on propose un schéma numérique avec une méthode de seuil efficace pour le problème de la retouche et très rapide en terme de temps de convergence. Ensuite, on étudie ce modèle avec des conditions de type Neumann sur le bord et une nonlinéarité singulière de type logarithmique et on donne des simulations numériques avec seuil qui confirment que les résultats obtenus avec une nonlinéarité de type logarithmique sont meilleurs que ceux obtenus avec une nonlinéarité de type polynomial. Finalement, on propose un modèle basé sur le système de Cahn-Hilliard pour la retouche d'images colorées. La deuxième partie de la thèse est consacrée à des applications en biologie et en chimie. On étudie la convergence de la solution d'une généralisation de l'équation de Cahn-Hilliard avec un terme de prolifération, associée à des conditions aux limites de type Neumann et une nonlinéarité régulière. Dans ce cas, on démontre que soit la solution explose en temps fini soit elle existe globalement en temps. Par ailleurs, on donne des simulations numériques qui confirment les résultats théoriques obtenus. On termine par l'étude de l'équation de Cahn-Hilliard avec un terme source et une nonlinéarité régulière. Dans cette étude, on considère le modèle à la fois avec des conditions aux limites de type Neumann et de type Dirichlet. / This thesis is situated in the context of the theoretical and numerical analysis of some generalizations of the Cahn-Hilliard equation. We study the well-possedness of these models, as well as the asymptotic behavior in terms of the existence of finite-dimenstional (in the sense of the fractal dimension) attractors. The first part of this thesis is devoted to some models which, in particular, have applications in image inpainting. We start by the study of the dynamics of the Bertozzi-Esedoglu-Gillette-Cahn-Hilliard equation with Neumann boundary conditions and a regular nonlinearity. We give numerical simulations with a fast numerical scheme with threshold which is sufficient to obtain good inpainting results. Furthermore, we study this model with Neumann boundary conditions and a logarithmic nonlinearity and we also give numerical simulations which confirm that the results obtained with a logarithmic nonlinearity are better than the ones obtained with a polynomial nonlinearity. Finally, we propose a model based on the Cahn-Hilliard system which has applications in color image inpainting. The second part of this thesis is devoted to some models which, in particular, have applications in biology and chemistry. We study the convergence of the solution of a Cahn-Hilliard equation with a proliferation term and associated with Neumann boundary conditions and a regular nonlinearity. In that case, we prove that the solutions blow up in finite time or exist globally in time. Furthermore, we give numericial simulations which confirm the theoritical results. We end with the study of the Cahn-Hilliard equation with a mass source and a regular nonlinearity. In this study, we consider both Neumann and Dirichlet boundary conditions.

The aim of this work was to develop an automated methods for removing unwanted objects from video sequences. The proposed method is able to autonomously tackle the static and the moving object with no user intervention into the process. The user only determines the object to deleted.